{"id":"https://openalex.org/W4416017153","doi":"https://doi.org/10.1145/3746252.3760794","title":"Leveraging Intra-Modal Consistency for Cross-Modal Alignment and Retrieval","display_name":"Leveraging Intra-Modal Consistency for Cross-Modal Alignment and Retrieval","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017153","doi":"https://doi.org/10.1145/3746252.3760794"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3760794","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3760794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fengyang Mao","orcid":"https://orcid.org/0009-0004-2486-6455"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengyang Mao","raw_affiliation_strings":["Sino-European School of Technology, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-2486-6455","affiliations":[{"raw_affiliation_string":"Sino-European School of Technology, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075095237","display_name":"Xiaodong Yue","orcid":"https://orcid.org/0000-0002-0536-1345"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Yue","raw_affiliation_strings":["Artificial Intelligence Institute, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0536-1345","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Institute, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107539182","display_name":"Yufei Chen","orcid":"https://orcid.org/0000-0002-3645-9046"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Chen","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3645-9046","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109486318","display_name":"Jiaqing Ma","orcid":"https://orcid.org/0009-0000-4991-9796"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqing Ma","raw_affiliation_strings":["Artificial Intelligence Institute, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-4991-9796","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Institute, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039502441","display_name":"Z.M. Zhang","orcid":"https://orcid.org/0009-0006-2590-4737"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheran Zhang","raw_affiliation_strings":["Sino-European School of Technology, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-2590-4737","affiliations":[{"raw_affiliation_string":"Sino-European School of Technology, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076351546","display_name":"Jie Shi","orcid":"https://orcid.org/0009-0000-4369-8400"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Shi","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-4369-8400","affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5026","last_page":"5030"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9406999945640564,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9406999945640564,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.03530000150203705,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.009600000455975533,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7856000065803528},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5708000063896179},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5546000003814697},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.531000018119812},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.43320000171661377},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4016000032424927},{"id":"https://openalex.org/keywords/similitude","display_name":"Similitude","score":0.38909998536109924},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3714999854564667}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7856000065803528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7723000049591064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5842000246047974},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5708000063896179},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5546000003814697},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.531000018119812},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4408999979496002},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.36329999566078186},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3760794","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3760794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2885775891","https://openalex.org/W3145807616","https://openalex.org/W3188030217","https://openalex.org/W3204670646","https://openalex.org/W4225414521","https://openalex.org/W4285606530","https://openalex.org/W4312372711","https://openalex.org/W4312655527","https://openalex.org/W4384661102","https://openalex.org/W4385767942","https://openalex.org/W4386072365","https://openalex.org/W4392384263","https://openalex.org/W4392678259","https://openalex.org/W4393158799","https://openalex.org/W4395447484"],"related_works":[],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,67,120,136],"aims":[2],"to":[3],"match":[4],"videos":[5],"and":[6,38,84,96,134],"texts":[7],"by":[8],"mapping":[9],"them":[10],"into":[11],"a":[12,51,75,90],"shared":[13,63,114],"feature":[14,132],"space.":[15,115],"Most":[16],"existing":[17],"approaches":[18],"achieve":[19],"alignment":[20],"through":[21],"contrastive":[22],"learning":[23],"based":[24],"on":[25,35,117],"one-to-one":[26],"supervised":[27,36],"pairs.":[28],"However,":[29],"these":[30],"methods":[31],"rely":[32],"too":[33],"much":[34],"signals":[37],"do":[39],"not":[40],"fully":[41],"use":[42],"the":[43,62,113,127,130],"unsupervised":[44],"semantic":[45],"relationships":[46],"within":[47],"each":[48],"modality.":[49],"As":[50],"result,":[52],"samples":[53,103],"that":[54,104,123],"are":[55,105],"semantically":[56],"similar":[57],"may":[58],"be":[59],"spread":[60],"in":[61,107,112],"space,":[64],"which":[65],"hurts":[66],"performance.":[68],"To":[69],"solve":[70],"this":[71,101],"problem,":[72],"we":[73],"propose":[74],"method":[76,88],"called":[77],"Leveraging":[78],"Intra-Modal":[79],"Consistency":[80],"for":[81],"Cross-Modal":[82],"Alignment":[83],"Retrieval":[85],"(LICA).":[86],"Our":[87],"introduces":[89],"consistency":[91],"constraint":[92],"between":[93],"intra-modal":[94],"similarities":[95],"cross-modal":[97,131],"similarity":[98],"distributions.":[99],"In":[100],"way,":[102],"close":[106],"meaning":[108],"stay":[109],"closer":[110],"together":[111],"Experiments":[116],"standard":[118],"text-video":[119],"benchmarks":[121],"show":[122],"LICA":[124],"helps":[125],"optimize":[126],"distribution":[128],"of":[129],"space":[133],"improves":[135],"accuracy.":[137]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-08T00:00:00"}